Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to legal sections or acts in official documents

    oai_token-act-pair · gpt-3.5-turbo

    references to legal sections and articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rous
    -0.68
    Reloaded
    -0.64
    bsite
    -0.63
    rose
    -0.59
    ighters
    -0.58
    robe
    -0.57
    tail
    -0.56
    larg
    -0.56
    tails
    -0.56
     Countdown
    -0.55
    POSITIVE LOGITS
     702
    1.11
     504
    1.10
     230
    1.07
     215
    1.06
     501
    1.06
     505
    1.03
     251
    1.03
     205
    1.02
     203
    1.01
     252
    1.01
    Act Density 0.041%

    No Known Activations